pith. sign in

arxiv: 2508.00208 · v3 · submitted 2025-07-31 · 💰 econ.GN · q-fin.EC

Channel Adoption Pathways and Post-Adoption Behavior

Shirsho Biswas , Hema Yoganarasimhan , Haonan Zhang This is my paper

Pith reviewed 2026-05-19 01:12 UTC · model grok-4.3

classification 💰 econ.GN q-fin.EC
keywords channel adoptionpost-adoption behaviormultichannel retailingadoption motivesforward buyingconsumer inertiacustomer profitabilitydifference-in-differences
0
0 comments X

The pith

Adoption motives for new shopping channels determine whether customers spend more and stay profitable long term.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper shows that customers who start shopping online increase their total spending compared with those who remain offline only. Yet the specific reason for adopting the new channel creates systematic differences in what happens next. Customers who adopt because of promotions tend to stock up early and then generate lower profits, while those who adopted during the COVID-19 pandemic keep using their original offline habits more often. These patterns matter for retailers that want accurate forecasts of customer value and better returns on the money spent to push customers online.

Core claim

Using transaction data from a Brazilian pet supplies retailer, the authors identify four adoption pathways—organic, COVID-19, Black Friday promotions, and loyalty program—and apply difference-in-differences estimation. All four groups increase spending after adoption, but promotion-driven adopters engage in forward buying and show lower subsequent profitability, whereas COVID-19 adopters exhibit stronger offline persistence consistent with consumer inertia and habit formation.

What carries the argument

Four cleanly separated adoption pathways analyzed through difference-in-differences to isolate the effect of adoption motive on post-adoption spend, profitability, and channel mix.

If this is right

  • Promotions meant to drive channel adoption should be structured to limit stockpiling if firms want to preserve later profitability.
  • Customers acquired through external shocks such as pandemics require habit-reinforcement tactics to increase long-term multichannel use.
  • Customer lifetime value forecasts and promotion ROI calculations must incorporate heterogeneity by adoption motive rather than treating all new online customers as equivalent.
  • Firms can improve breakeven analysis of channel-expansion spending by weighting different acquisition pathways according to their distinct post-adoption trajectories.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same motive-based segmentation could be applied to other product categories where transaction histories are available.
  • Targeted digital nudges might be tested to convert one-time promotion adopters into more habitual multichannel users.
  • Distinguishing temporary versus enduring channel shifts could help refine models of customer inertia beyond the current setting.

Load-bearing premise

The transaction records allow the four pathways to be identified without meaningful overlap, and the difference-in-differences design removes pre-existing customer differences so that observed behavior gaps reflect the adoption motive itself.

What would settle it

If adding finer pre-adoption customer controls eliminates the profitability gap between promotion and COVID-19 adopters, or if the data show no forward buying among promotion adopters, the central claim would be undermined.

Figures

Figures reproduced from arXiv: 2508.00208 by Haonan Zhang, Hema Yoganarasimhan, Shirsho Biswas.

Figure 2
Figure 2. Figure 2: Share of offline spend relative to total spend – [PITH_FULL_IMAGE:figures/full_fig_p034_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Monthly Total Spend Visualization – Black Friday/Loyalty Program vs. Organic Adopters. (a) Black Friday (b) Loyalty Program Thus, based on the theory of forward buying during promotions and our empirical findings, managers should not expect as high a post-adoption spend for promotion-driven adopters of online shopping relative to organic adopters. 23Notably, if we only look at offline spending (see Figure … view at source ↗
read the original abstract

The rapid growth of digital shopping channels has prompted many traditional retailers to invest in e-commerce websites and mobile apps. While prior literature shows that multichannel customers are more valuable, it overlooks how the motive for adopting a new channel shapes post-adoption behavior. Using transaction-level data from a major Brazilian pet supplies retailer, we study offline-only consumers who adopt online shopping via four distinct pathways: organic adoption, the COVID-19 pandemic, Black Friday promotions, and a loyalty program. We examine how these pathways affect post-adoption spend, profitability, and channel usage using consumer-level panel data and difference-in-differences estimates. We find that all adopters increase spending relative to offline-only consumers, but their post-adoption behaviors differ systematically by adoption motive. Promotion-driven adopters engage in forward buying and exhibit lower subsequent profitability, whereas COVID-19 adopters display stronger offline persistence consistent with consumer inertia and habit theory. Our findings have important managerial implications: firms should design promotions that discourage stockpiling, reinforce habits among customers pushed online by external shocks, and explicitly account for heterogeneity in channel adoption motives when forecasting customer lifetime value and assessing the breakeven and ROI of promotions designed to induce the adoption of new channels.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper uses transaction-level panel data from a Brazilian pet supplies retailer to study offline-only consumers who adopt online channels via four pathways (organic, COVID-19, Black Friday promotions, loyalty program). Difference-in-differences estimates show all adopters increase spending relative to non-adopters, but promotion-driven adopters exhibit forward buying and lower subsequent profitability while COVID-19 adopters display stronger offline persistence, with implications for promotion design and CLV forecasting.

Significance. If the identification strategy is valid, the work contributes to multichannel retailing literature by documenting motive-driven heterogeneity in post-adoption behavior rather than treating multichannel customers as homogeneous. The managerial implications for avoiding stockpiling in promotions and reinforcing habits after external shocks are concrete and testable.

major comments (2)
  1. [Empirical Strategy] Empirical identification section: the DiD comparisons of each pathway group to offline-only controls do not report group-specific pre-trend tests, covariate balance on pre-adoption spending or margins, or selection-on-observables checks. Because promotion adopters are plausibly more deal-prone ex ante, this leaves open whether lower post-adoption profitability and forward buying reflect the promotion motive or pre-existing customer types.
  2. [Main Results] Results on profitability and channel persistence: the reported heterogeneity across pathways is central to the claim, yet the manuscript provides no details on robustness to alternative control groups, winsorization, or corrections for multiple testing across the four pathways.
minor comments (2)
  1. [Abstract] Abstract: add one sentence on sample construction, time window, and whether parallel-trends or balance diagnostics were performed.
  2. [Variable Definitions] Notation: clarify how 'forward buying' is operationalized (e.g., inter-purchase time or quantity spikes) and how profitability is measured (margin per transaction or contribution margin).

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive comments. We respond to each major comment below, indicating the changes we will implement in the revised version of the manuscript.

read point-by-point responses

  1. Referee: [Empirical Strategy] Empirical identification section: the DiD comparisons of each pathway group to offline-only controls do not report group-specific pre-trend tests, covariate balance on pre-adoption spending or margins, or selection-on-observables checks. Because promotion adopters are plausibly more deal-prone ex ante, this leaves open whether lower post-adoption profitability and forward buying reflect the promotion motive or pre-existing customer types.

    Authors: We agree that reporting group-specific pre-trend tests, covariate balance on pre-adoption spending and margins, and selection-on-observables checks would strengthen the identification. In the revised manuscript we will add event-study specifications to test parallel trends separately for each of the four adoption pathways. We will also include balance tables on pre-adoption observables, including past promotion usage and spending levels, and will report robustness results from propensity-score matching to address potential selection on deal-proneness. These additions will help separate the role of adoption motive from pre-existing customer heterogeneity. revision: yes

  2. Referee: [Main Results] Results on profitability and channel persistence: the reported heterogeneity across pathways is central to the claim, yet the manuscript provides no details on robustness to alternative control groups, winsorization, or corrections for multiple testing across the four pathways.

    Authors: We acknowledge the value of additional robustness checks for the heterogeneity results. The revised manuscript will contain an expanded robustness section that reports estimates using alternative control groups (including propensity-score matched samples), results under alternative winsorization thresholds, and p-values adjusted for multiple testing across the four pathways via Bonferroni and false-discovery-rate procedures. These checks will confirm that the documented differences in forward buying, profitability, and channel persistence are not sensitive to these specification choices. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical DiD on external retailer data with no self-referential reductions

full rationale

The paper defines adoption pathways from observable timing (COVID period, Black Friday) or program enrollment in external transaction data, then applies standard difference-in-differences to compare post-adoption outcomes against offline-only controls. No equations, fitted parameters, or derivations are shown that reduce reported effects or heterogeneity claims to inputs by construction. Central results rest on external data and conventional econometric identification rather than self-citations, ansatzes, or uniqueness theorems imported from the authors' prior work. This is a self-contained empirical study whose claims do not collapse into tautological fits or renamings.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

Analysis rests on standard econometric assumptions for difference-in-differences; no free parameters or invented entities are described in the abstract.

axioms (1)
  • domain assumption Difference-in-differences identifies causal effects of adoption pathway under the parallel trends assumption
    Invoked implicitly by the use of DiD on pre/post adoption panel data.

pith-pipeline@v0.9.0 · 5744 in / 1269 out tokens · 41221 ms · 2026-05-19T01:12:25.200485+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

12 extracted references · 12 canonical work pages

  1. [1]

    Mostly Harmless Econometrics (Princeton Uni,

    Angrist, Joshua and Joern-Steffen Pischke “Mostly Harmless Econometrics (Princeton Uni,” (2008)

    work page 2008

  2. [2]

    Customer channel migration,

    Ansari, Asim, Carl F Mela, and Scott A Neslin (2008), “Customer channel migration,” Journal of Marketing Research, 45 (1), 60–76

    work page 2008

  3. [3]

    Difference-in-differences with multiple time periods,

    Callaway, Brantly and Pedro HC Sant’Anna (2021), “Difference-in-differences with multiple time periods,” Journal of Econometrics, 225 (2), 200–230

    work page 2021

  4. [4]

    Browsing the aisles or browsing the app? how online grocery shopping is changing what we buy,

    Chintala, Sai Chand, J¯ura Liaukonyt˙e, and Nathan Yang (2023), “Browsing the aisles or browsing the app? how online grocery shopping is changing what we buy,”Marketing Science

    work page 2023

  5. [5]

    Use of quasi-experimental research designs in education research: Growth, promise, and challenges,

    Gopalan, Maithreyi, Kelly Rosinger, and Jee Bin Ahn (2020), “Use of quasi-experimental research designs in education research: Growth, promise, and challenges,” Review of Research in Education, 44 (1), 218–243

    work page 2020

  6. [6]

    Who are the multichannel shoppers and how do they perform?: Correlates of multichannel shopping behavior,

    Kumar, Vipin and Rajkumar Venkatesan (2005), “Who are the multichannel shoppers and how do they perform?: Correlates of multichannel shopping behavior,” Journal of Interactive Marketing, 19 (2), 44–62

    work page 2005

  7. [7]

    Are multichannel customers really more valuable? The moderating role of product category characteristics,

    Kushwaha, Tarun and Venkatesh Shankar (2013), “Are multichannel customers really more valuable? The moderating role of product category characteristics,” Journal of Marketing, 77 (4), 67–85

    work page 2013

  8. [8]

    A more credible approach to parallel trends,

    Rambachan, Ashesh and Jonathan Roth (2023), “A more credible approach to parallel trends,” Review of Economic Studies, 90 (5), 2555–2591

    work page 2023

  9. [9]

    Constructing a control group using multivariate matched sampling methods that incorporate the propensity score,

    Rosenbaum, Paul R and Donald B Rubin (1985), “Constructing a control group using multivariate matched sampling methods that incorporate the propensity score,” The American Statistician, 39 (1), 33–38. Sant’Anna, Pedro HC and Jun Zhao (2020), “Doubly robust difference-in-differences estimators,”Journal of Econometrics, 219 (1), 101–122

    work page 1985

  10. [10]

    MatchIt: nonparametric preprocessing for parametric causal inference,

    Stuart, Elizabeth A, Gary King, Kosuke Imai, and Daniel Ho (2011), “MatchIt: nonparametric preprocessing for parametric causal inference,” Journal of statistical software

    work page 2011

  11. [11]

    Managing marketing communications with multichannel customers,

    Thomas, Jacquelyn S and Ursula Y Sullivan (2005), “Managing marketing communications with multichannel customers,” Journal of Marketing, 69 (4), 239–251. Trading Economics “Brazil Sales Tax Rate,” https://tradingeconomics.com/brazil/ sales-tax-rate (2025) Accessed: 2025-07-24

    work page 2005

  12. [12]

    Multichannel shopping: causes and consequences,

    Venkatesan, Rajkumar, Vipin Kumar, and Nalini Ravishanker (2007), “Multichannel shopping: causes and consequences,” Journal of Marketing, 71 (2), 114–132. lxvii

    work page 2007